Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 2.111

Biomedical informatics and panomics for evidence‐based radiation therapy

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

More than half of all cancer patients receive ionizing radiation as part of their treatment. Treatment outcomes are determined by complex interactions between cancer genetics, treatment regimens, and patient‐related variables. A key component of modern radiation oncology research is to predict at the time of treatment planning or during the course of fractionated radiation treatment, the probability of tumor eradication and normal tissue risks for the type of treatment being considered for the individual patient. A typical radiotherapy treatment scenario can generate a large pool of panomics data that may comprise 3D/4D anatomical and functional imaging information (noted as radiomics), in addition to biological markers (genomics, proteomics, metabolomics, etc.) derived from peripheral blood and tissue specimens. Radiotherapy data informatics constitutes a unique interface between physical and biological processes. It can benefit from the general advances in biomedical informatics research while still requires the development of its own technologies within this framework to address specific issues related to its unique physics–biology interface. We review recent advances and discuss current challenges to interrogate panomics data in radiotherapy using bioinformatics tools for data aggregation, sharing, visualization, and outcomes modeling. We provide examples based on our and others experiences using systems radiobiology and machine learning to develop predictive models of outcomes in radiotherapy. We also highlight the potential opportunities in this field for evidence‐based personalized medicine research for bioinformaticians and clinical decision‐makers.

Understanding of heterogeneous variables interactions as a feedback loop into the treatment planning system to adaptively improve patient's outcomes.
[ Normal View | Magnified View ]
Graph‐based approach for identifying robust biomarkers from limited proteomics sample‐size data. The example shows the identification of alpha‐2‐macroglobulin (α2M) by analyzing proteomics data of 3 × 3 matched pair patients with and without radiation pneumonitis (RP) using a novel graph‐based approach.
[ Normal View | Magnified View ]
Top: A Bayesian network with probability tables for combined biomarker proteins and physical variables for modeling local tumor control in lung cancer. Bottom: The binning boundaries for each variable.
[ Normal View | Magnified View ]
Multiscale‐modeling framework of tissue (tumor) radiation response along the time and space axes.
[ Normal View | Magnified View ]

Related Articles

Cancer: An Interdisciplinary View

Browse by Topic

Algorithmic Development > Biological Data Mining
Application Areas > Health Care

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts